1 citations · 2 across the 8 of their papers we have counts for
12 papers
Trained Agentic Context Management
Bryce Sandlund
We study long context language models. Instead of training long context natively, or designing a long context harness, we train a model over the simplest possible harness: a tool t…
Sharp Minima Can Generalize: A Loss Landscape Perspective On Data
Raymond Fan, Bryce Sandlund, Lin Myat Ko
The volume hypothesis suggests deep learning is effective because it is likely to find flat minima due to their large volumes, and flat minima generalize well. This picture does no…
Selectable Heaps and Optimal Lazy Search Trees
Bryce Sandlund, Lingyi Zhang
We show the time extract minimum function of efficient priority queues can be generalized to the extraction of the smallest elements in time (we de…
Lazy Search Trees
Bryce Sandlund, Sebastian Wild
We introduce the lazy search tree data structure. The lazy search tree is a comparison-based data structure on the pointer machine that supports order-based operations such as rank…
Faster Dynamic Range Mode
Bryce Sandlund, Yinzhan Xu
In the dynamic range mode problem, we are given a sequence of length bounded by and asked to support element insertion, deletion, and queries for the most frequent element…
A Simple Algorithm for Minimum Cuts in Near-Linear Time
Nalin Bhardwaj, Antonio Molina Lovett, Bryce Sandlund
We consider the minimum cut problem in undirected, weighted graphs. We give a simple algorithm to find a minimum cut that -respects (cuts two edges of) a spanning tree of a…